A Metamodel-Assisted Steady-State Evolution Strategy for Simulation-Based Optimization

  • Anna Person
  • Henrik Grimm
  • Amos Ng
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 6)

Evolutionary algorithms (EAs) have proven to be highly useful for optimization of real-world problems due to their powerful ability to find near-optimal solutions of complex problems [8]. A variety of successful applications of EAs has been reported for problems such as engineering design, operational planning, and scheduling.However, in spite of the great success achieved in many applications, EAs have also encountered some challenges. The main weakness of using EAs in real-worldoptimization is that a large number of simulation evaluations are needed before anacceptable solution can be found. Typically, an EA requires thousands of simulation evaluations and one single evaluation may take a couple of minutes to hoursof computing time. This poses a serious hindrance to the practical application of EAs in real-world scenarios, and to address this problem the incorporation of computationally efficient metamodels has been suggested, so-called metamodel-assisted EAs [11]. The purpose of metamodels is to approximate the relationship between the input and output variables of a simulation by computationally efficient mathematical models.

This chapter presents a new metamodel-assisted EA for optimization of computationally expensive simulation-optimization problems. The proposed algorithm is basically an evolution strategy inspired by concepts from genetic algorithms. For maximum parallelism and increased efficiency, the algorithm uses a steady-state design. The chapter describes how the algorithm is successfully applied to optimize two real-world problems in the manufacturing domain. The first problem considered is about optimal buffer allocation in a car engine production line, and the second problem considered is about optimal production scheduling in a manufacturing cell for aircraft engines. In both problems, artificial neural networks (ANNs) are used as the metamodel.


Tournament Selection Manufacturing Cell Cylinder Block Simulation Evaluation Buffer Allocation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Beyer, H.G., Schwefel, H.P. (2002) Evolution strategies—A comprehensive introduction. Natural Computing 1(1), pp. 3–52.MATHCrossRefMathSciNetGoogle Scholar
  2. 2.
    Bull, L. (1999) On model-based evolutionary computation. Software Computing (3), pp. 76–82.Google Scholar
  3. 3.
    Fonseca, D.J., Navaresse, D.O., Moynihan, G.P. (2003) Simulation metamodeling through artificial neural networks. Engineering Applications of Artificial Intelligence 16(3), pp. 177–183.CrossRefGoogle Scholar
  4. 4.
    Holland, J.H. (1975) Adaptation in Natural and Artificial Systems, University of Michigan Press, Ann Arbor.Google Scholar
  5. 5.
    Hüsken, M., Jin, Y., Sendhoff, B. (2005) Structure optimization of neural networks for evolutionary design optimization. Source Soft Computing—A Fusion of Foundations, Methodologies and Applications 9(1), pp. 21–28.Google Scholar
  6. 6.
    Jin, Y., Olhofer, M., Sendhoof, B. (2002) A framework for evolutionary optimization with approximate fitness functions. IEEE Transactions on Evolutionary Computation 6(5), pp. 481–494.CrossRefGoogle Scholar
  7. 7.
    Khu, S.T., Savic, D., Liu, Y., Madsen, H. (2004) A fast evolutionary-based metamodelling approach for the calibration of a rainfall-runoff model. In: Proceedings of the First Biennial Meeting of the International Environmental Modelling and Software Society, pp. 147–152, Osnabruck, Germany.Google Scholar
  8. 8.
    Laguna, M., Marti, R. (2002) Neural network prediction in a system for optimizing simulations. IEEE Transactions (34), pp. 273–282.Google Scholar
  9. 9.
    Lim, D., Ong, Y.-S., Lee, B.-S. (2005) Inverse multi-objective robust evolutionary design optimization in the presence of uncertainty. In: Proceedings of the 2005 Workshops on Genetic and Evolutionary Computation, pp. 55–62, Washington, DC.Google Scholar
  10. 10.
    Ng, A., Grimm, H., Lezama, T., Persson, A., Andersson, M., Jägstam, M. (2007) Web services for metamodel-assisted parallel simulation optimization. In: Proceedings of The IAENG International Conference on Internet Computing and Web Services (ICICWS’07), March 21–23, pp. 879–885, Hong Kong.Google Scholar
  11. 11.
    Ong, Y.S., Nair, P.B., Keane, A.J., Wong, K.W. (2004) Surrogate-assisted evolutionary optimization frameworks for high-fidelity engineering design problems. In: Knowledge Incorporation in Evolutionary Computation, pp. 307–332, Springer, New York.Google Scholar
  12. 12.
    Ulmer, H., Streichert, F., Zell, A. (2003) Evolution strategies assisted by Gaussian processes with improved pre-selection criterion. In: Proceedings of IEEE Congress on Evolutionary Computation (CEC’03), December 8–12, 2003, pp. 692–699, Canberra, Australia.Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2008

Authors and Affiliations

  • Anna Person
    • 1
  • Henrik Grimm
    • 1
  • Amos Ng
    • 1
  1. 1.Centre for Intelligent AutomationUniversity of SkövdeSweden

Personalised recommendations